Module zero_sum::impls::tak::evaluator

Contains evaluators for tak states.

Structs

AnnEvaluator	Uses an artificial neural network to evaluate the tak state. The network has three hidden layers using ReLU activation, and uses TanH activation on the output. It uses ADADELTA to perform gradient descent.
StaticEvaluator	Provides a static evaluation of a tak state. This evaluator considers top-level pieces, stacked flatstones, road-group size, one-away threats, and stack influence.